Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 8748
    Prev
    Next
    INDEX
    Explanations

    specific nouns or noun phrases related to events, decisions, and actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to official announcements and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atever
    -0.62
    riv
    -0.55
    hett
    -0.52
    arte
    -0.51
    oslav
    -0.50
    ij士
    -0.49
    ovy
    -0.49
    inker
    -0.48
    ussy
    -0.48
    ophers
    -0.46
    POSITIVE LOGITS
     weeks
    1.11
     shortly
    1.11
     Wednesday
    1.05
     Tuesday
    1.05
     yesterday
    1.05
     Monday
    1.04
     Thursday
    1.04
     Friday
    1.01
     hours
    0.99
     days
    0.98
    Activations Density 0.432%

    No Known Activations